Compressing Pre-trained Models of Code into 3 MB

Jieke Shi, Zhou Yang, Bowen Xu, Hong Jin Kang, David Lo

Abstract

Although large pre-trained models of code have delivered significant advancements in various code processing tasks, there is an impediment to the wide and fluent adoption of these powerful models in software developers’ daily workflow: these large models consume hundreds of megabytes of memory and run slowly on personal devices, which causes problems in model deployment and greatly degrades the user experience.

BibTeX

@inproceedings{Shi-al:ASE22,
  author    = {Jieke Shi and
               Zhou Yang and
               Bowen Xu and
               Hong Jin Kang and
               David Lo},
  title     = {Compressing Pre-trained Models of Code into 3 {MB}},
  booktitle = {ASE},
  pages     = {24:1--24:12},
  publisher = {{ACM}},
  year      = {2022},
}

Compressing Pre-trained Models of Code into 3 MB

Abstract

Related papers